Designing molecules that bind to specific target proteins is a fundamental task in drug discovery. Recent models leverage geometric constraints to generate ligand molecules that bind cohesively with specific protein pockets. However, these models cannot effectively generate 3D molecules with 2D skeletal curtailments and property constraints, which are pivotal to drug potency and development. To tackle this challenge, we propose GraphVF, a variational flow-based framework that combines 2D topology and 3D geometry, for controllable generation of binding 3D molecules. Empirically, our method achieves state-of-the-art binding affinity and realistic sub-structural layouts for protein-specific generation. In particular, GraphVF represents the first controllable geometry-aware, protein-specific molecule generation method, which can generate binding 3D molecules with tailored sub-structures and physio-chemical properties. Our code is available at https://github.com/Franco-Solis/GraphVF-code.
@article{arxiv.2304.12825,
title = {GraphVF: Controllable Protein-Specific 3D Molecule Generation with Variational Flow},
author = {Fang Sun and Zhihao Zhan and Hongyu Guo and Ming Zhang and Jian Tang},
journal= {arXiv preprint arXiv:2304.12825},
year = {2023}
}